Sean Sprague wrote:
Bryan,
[Snip!]
And there you have it. To verify Matt's hypothesis, run the DTrace
one-liner that I sent you; if it's the bug that Matt suggested (which
certainly matches the symptoms you describe), you'll see stack traces
like this one in the output:
issig_forreal+0x5c0()
cv_wait_sig+0x190()
snf_segmap+0x450()
sosendfile64+0x2a0()
sendvec64+0xf0()
sendfilev+0x178()
syscall_trap32+0xcc()
Would you mind at all to publish the one-liner here (for those of us
who can't guess what it is ;-) )?
Actually, he did in the message at 10:45PM PST:
# dtrace -n profile-1234hz'/pid == 4308/[EMAIL PROTECTED]()] = count()}
Interestingly, the only difference between that and one Ben had tried is
he used stack() instead of ustack(), which is much more appropriate for
this situation. The problem was there never was a return from the
syscall, so you couldn't really expect to examine the ustack().
- Matt
_______________________________________________
opensolaris-discuss mailing list
[email protected]
